Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1396. Min Range: -3.1396
Max Act: 3.1396. Min Act: -0.1700
Data Index: 589868 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.9026. Min Act: -0.1700
Data Index: 8133804 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.9026. Min Act: -0.1700
Data Index: 5181097 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.8709. Min Act: -0.1700
Data Index: 6907244 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.8391. Min Act: -0.1700
Data Index: 3051497 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7755. Min Act: -0.1700
Data Index: 1272617 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7755. Min Act: -0.1700
Data Index: 97186 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7755. Min Act: -0.1700
Data Index: 2302377 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7755. Min Act: -0.1700
Data Index: 1269159 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7435. Min Act: -0.1700
Data Index: 2064492 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7435. Min Act: -0.1700
Data Index: 7856244 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7435. Min Act: -0.1700
Data Index: 4645042 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7276. Min Act: -0.1700
Data Index: 2721118 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7276. Min Act: -0.1700
Data Index: 1063273 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7276. Min Act: -0.1700
Data Index: 5826690 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7116. Min Act: -0.1700
Data Index: 4113430 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7276. Min Act: -0.1700
Data Index: 6743861 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.7116. Min Act: -0.1700
Data Index: 5357565 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.6956. Min Act: -0.1700
Data Index: 7136300 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1396. Min Range: -3.1396
Max Act: 2.6956. Min Act: -0.1700
Data Index: 8505900 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19